Explore the vast range of titles available.

A brain tumour is one of the major reasons for death in humans, and it is the tenth most common type of tumour that affects people of all ages. However, if detected early, it is one of the most treatable types of tumours. Brain tumours are classified using biopsy, which is not usually performed before definitive brain surgery. An image classification technique for tumour diseases is important for accelerating the treatment process and avoiding surgery and errors from manual diagnosis by radiologists. The advancement of technology and machine learning (ML) can assist radiologists in tumour diagnostics using magnetic resonance imaging (MRI) images without invasive procedures. This work introduced a new hybrid CNN-based architecture to classify three brain tumour types through MRI images. The method suggested in this paper uses hybrid deep learning classification based on CNN with two methods. The first method combines a pre-trained Google-Net model of the CNN algorithm for feature extraction with SVM for pattern classification. The second method integrates a finely tuned Google-Net with a soft-max classifier. The proposed approach was evaluated using MRI brain images that contain a total of 1426 glioma images, 708 meningioma images, 930 pituitary tumour images, and 396 normal brain images. The reported results showed that an accuracy of 93.1% was achieved from the finely tuned Google-Net model. However, the synergy of Google-Net as a feature extractor with an SVM classifier improved recognition accuracy to 98.1%.

Simulated annealing (SA) was recognized as an effective local search optimizer, and it showed a great success in many real-world optimization problems. However, it has slow convergence rate and its performance is widely affected by the settings of its parameters, namely the annealing factor and the mutation rate. To mitigate these limitations, this study presents an enhanced optimizer that integrates Q-learning algorithm with SA in a single optimization model, named QLSA. In particular, the Q-learning algorithm is embedded into SA to enhance its performances by controlling its parameters adaptively at run time. The main characteristics of Q-learning are that it applies reward/penalty technique to keep track of the best performing values of these parameters, i.e., annealing factor and the mutation rate. To evaluate the effectiveness of the proposed QLSA algorithm, a total of seven constrained engineering design problems were used in this study. The outcomes show that QLSA was able to report a mean fitness value of 1.33 on cantilever beam design, 263.60 on three-bar truss design, 1.72 on welded beam design, 5905.42 on pressure vessel design, 0.0126 on compression coil spring design, 0.25 on multiple disk clutch brake design, and 2994.47 on speed reducer design problem. Further analysis was conducted by comparing QLSA with the state-of-the-art population optimization algorithms including PSO, GWO, CLPSO, harmony, and ABC. The reported results show that QLSA significantly (i.e., 95% confidence level) outperforms other studied algorithms.

The global prevalence of skin cancer necessitates the development of AI‐assisted technologies for accurate and interpretable diagnosis of skin lesions. This study presents a novel deep learning framework for enhancing the interpretability and reliability of skin lesion predictions from clinical images, which are more inclusive, accessible, and representative of real‐world conditions than dermoscopic images. We comprehensively analyzed 13 deep learning models from four main convolutional neural network architecture classes: DenseNet, ResNet, MobileNet, and EfficientNet. Different data augmentation strategies and model optimization algorithms were explored to access the performances of the deep learning models in binary and multiclass classification scenarios. In binary classification, the DenseNet‐161 model, initialized with random weights, obtained a top accuracy of 79.40%, while the EfficientNet‐B7 model, initialized with pretrained weights from ImageNet, reached an accuracy of 85.80%. Furthermore, in the multiclass classification experiments, DenseNet121, initialized with random weights and trained with AdamW, obtained the best accuracy of 65.1%. Likewise, when initialized with pretrained weights, the DenseNet121 model attained a top accuracy of 75.07% in multiclass classification. Detailed interpretability analyses were carried out leveraging the SHAP and CAM algorithms to provide insights into the decision rationale of the investigated models. The SHAP algorithm was beneficial in understanding the feature attributions by visualizing how specific regions of the input image influenced the model predictions. Our study emphasizes using clinical images for developing AI algorithms for skin lesion diagnosis, highlighting the practicality and relevance in real‐world applications, especially where dermoscopic tools are not readily accessible. Beyond accessibility, these developments also ensure that AI‐assisted diagnostic tools are deployed in diverse clinical settings, thus promoting inclusiveness and ultimately improving early detection and treatment of skin cancers.

In this work, a hybrid optimization-based model is introduced to handle the problem of face sketch recognition. The proposed model comprises a total of three layers that are global search layer, control layer, and fine-tuning layer. The global layer contains a set of search operations from particle swarm optimization (PSO) algorithm to perform the task of global search. However, the control layer is responsible about controlling the execution of the implemented search operations at run time. Finally, the fine-tuning layer is aimed at performing search refinement to enhance the search ability. For sketch recognition, the proposed hybrid model is applied on the input face sketch to locate the internal sketch facial components. Three types of texture features extraction techniques are adopted in this study including Histogram Of Gradient (HOG), Local Binary Pattern (LBP), and Gabor wavelet. To assess the performances of the proposed model, a total of three face sketch databases have been used which are LFW, AR, and CUHK. The reported results indicate that the proposed hybrid model was able to achieve a competitive performance with 96% on AR, 87.68% on CUHK, and 50.00% on LFW. Additionally, the outcomes reveal that the proposed model statistically outperforms others PSO-based models as well as the state-of-the-art meta-heuristic optimization models.

There are many pre-trained deep learning-based face recognition models developed in the literature, such as FaceNet, ArcFace, VGG-Face, and DeepFace. However, performing transfer learning of these models for handling face sketch recognition is not applicable due to the challenge of limited sketch datasets (single sketch per subject). One promising solution to mitigate this issue is by using optimization algorithms, which will perform a fine-tuning and fitting of these models for the face sketch problem. Specifically, this research introduces an enhanced optimizer that will evolve these models by performing automatic weightage/fine-tuning of the generated feature vector guided by the recognition accuracy of the training data. The following are the key contributions to this work: (i) this paper introduces a novel Smart Switching Slime Mold Algorithm (S2SMA), which has been improved by embedding several search operations and control rules; (ii) the proposed S2SMA aims to fine-tune the pre-trained deep learning models in order to improve the accuracy of the face sketch recognition problem; and (iii) the proposed S2SMA makes simultaneous fine-tuning of multiple pre-trained deep learning models toward further improving the recognition accuracy of the face sketch problem. The performance of the S2SMA has been evaluated on two face sketch databases, which are XM2VTS and CUFSF, and on CEC’s 2010 large-scale benchmark. In addition, the outcomes were compared to several variations of the SMA and related optimization techniques. The numerical results demonstrated that the improved optimizer obtained a higher level of fitness value as well as better face sketch recognition accuracy. The statistical data demonstrate that S2SMA significantly outperforms other optimization techniques with a rapid convergence curve.

There are several benefits to constructing a lightweight vision system that is implemented directly on limited hardware devices. Most deep learning-based computer vision systems, such as YOLO (You Only Look Once), use computationally expensive backbone feature extractor networks, such as ResNet and Inception network. To address the issue of network complexity, researchers created SqueezeNet, an alternative compressed and diminutive network. However, SqueezeNet was trained to recognize 1000 unique objects as a broad classification system. This work integrates a two-layer particle swarm optimizer (TLPSO) into YOLO to reduce the contribution of SqueezeNet convolutional filters that have contributed less to human action recognition. In short, this work introduces a lightweight vision system with an optimized SqueezeNet backbone feature extraction network. Secondly, it does so without sacrificing accuracy. This is because that the high-dimensional SqueezeNet convolutional filter selection is supported by the efficient TLPSO algorithm. The proposed vision system has been used to the recognition of human behaviors from drone-mounted camera images. This study focused on two separate motions, namely walking and running. As a consequence, a total of 300 pictures were taken at various places, angles, and weather conditions, with 100 shots capturing running and 200 images capturing walking. The TLPSO technique lowered SqueezeNet’s convolutional filters by 52%, resulting in a sevenfold boost in detection speed. With an F1 score of 94.65% and an inference time of 0.061 milliseconds, the suggested system beat earlier vision systems in terms of human recognition from drone-based photographs. In addition, the performance assessment of TLPSO in comparison to other related optimizers found that TLPSO had a better convergence curve and achieved a higher fitness value. In statistical comparisons, TLPSO surpassed PSO and RLMPSO by a wide margin.

You only look once (YOLO) is a state-of-the-art object detection model which has a novel architecture that balances model complexity with the inference time. Among YOLO versions, YOLOv7 has a lightweight backbone network called E-ELAN that allows it to learn more efficiently without affecting the gradient path. However, YOLOv7 models face classification difficulties when dealing with classes that have a similar shape and texture like personal protective equipment (PPE). In other words, the Glass versus NoGlass PPE objects almost appear similar when the image is captured at a distance. To mitigate this issue and further improve the classification performance of YOLOv7, a modified version called the contrastive-based model is introduced in this work. The basic concept is that a contrast loss branch function has been added, which assists the YOLOv7 model in differentiating and pushing instances from different classes in the embedding space. To validate the effectiveness of the implemented contrastive-based YOLO, it has been evaluated on two different datasets which are CHV and our own indoor collected dataset named JRCAI. The dataset contains 12 different types of PPE classes. Notably, we have annotated both datasets for the studied 12 PPE objects. The experimental results showed that the proposed model outperforms the standard YOLOv7 model by 2% in mAP@0.5 measure. Furthermore, the proposed model outperformed other YOLO variants as well as cutting-edge object detection models such as YOLOv8, Faster-RCNN, and DAB-DETR.

According to the World Health Organization, millions of infections and a lot of deaths have been recorded worldwide since the emergence of the coronavirus disease (COVID-19). Since 2020, a lot of computer science researchers have used convolutional neural networks (CNNs) to develop interesting frameworks to detect this disease. However, poor feature extraction from the chest X-ray images and the high computational cost of the available models introduce difficulties for an accurate and fast COVID-19 detection framework. Moreover, poor feature extraction has caused the issue of ‘the curse of dimensionality’, which will negatively affect the performance of the model. Feature selection is typically considered as a preprocessing mechanism to find an optimal subset of features from a given set of all features in the data mining process. Thus, the major purpose of this study is to offer an accurate and efficient approach for extracting COVID-19 features from chest X-rays that is also less computationally expensive than earlier approaches. To achieve the specified goal, we design a mechanism for feature extraction based on shallow conventional neural network (SCNN) and used an effective method for selecting features by utilizing the newly developed optimization algorithm, Q-Learning Embedded Sine Cosine Algorithm (QLESCA). Support vector machines (SVMs) are used as a classifier. Five publicly available chest X-ray image datasets, consisting of 4848 COVID-19 images and 8669 non-COVID-19 images, are used to train and evaluate the proposed model. The performance of the QLESCA is evaluated against nine recent optimization algorithms. The proposed method is able to achieve the highest accuracy of 97.8086% while reducing the number of features from 100 to 38. Experiments prove that the accuracy of the model improves with the usage of the QLESCA as the dimensionality reduction technique by selecting relevant features. Graphical abstract

Harris Hawks Optimizer (HHO) is a recent optimizer that was successfully applied for various real-world problems. However, working under large-scale problems requires an efficient exploration/exploitation balancing scheme that helps HHO to escape from possible local optima stagnation. To achieve this objective and boost the search efficiency of HHO, this study develops embedded rules used to make adaptive switching between exploration/exploitation based on search performances. These embedded rules were formulated based on several parameters such as population status, success rate, and the number of consumed search iterations. To verify the effectiveness of these embedded rules in improving HHO performances, a total of six standard high-dimensional functions ranging from 1000-D to 10,000-D and CEC’2010 large-scale benchmark were employed in this study. In addition, the proposed Rules Embedded Harris Hawks Optimizer (REHHO) applied for one real-world high dimensional wavelength selection problem. Conducted experiments showed that these embedded rules significantly improve HHO in terms of accuracy and convergence curve. In particular, REHHO was able to achieve superior performances against HHO in all conducted benchmark problems. Besides that, results showed that faster convergence was obtained from the embedded rules. Furthermore, REHHO was able to outperform several recent and state-of-the-art optimization algorithms.

Pedestrian detection from a drone-based images has many potential applications such as searching for missing persons, surveillance of illegal immigrants, and monitoring of critical infrastructure. However, it is considered as a very challenge computer vision problem due to the variations in camera point of view, distance from pedestrian, changes in illuminations and weather conditions, variation in the surrounding objects, as well as present of human-like objects. Recently, deep learning-based models are getting more attention, and they have proven a great success in many object detection problems such as the detection of faces, breast masses, and vehicles. As such, this work aims to develop a deep learning-based model that will be applied for the problem of pedestrian detection from a drone-based images. Particularly, faster region-based convolutional neural network (Faster R-CNN) will be used to search for the present of a pedestrian inside the captured drone-based images. To assess the performances, a total of 1500 images were collected by S30W drone and these images were captured at different places, with various views and weather conditions, and at daytime and night-time. Results show that Faster R-CNN was able to achieve a promising result with 98% precision, 99% recall, and 98% F 1 measure. Further analysis has been conducted by comparing the outcomes of Faster R-CNN with YOLO deep model on UAV123 publicly available dataset. The reported results indicated that both detection models almost reported very similar results.